EdgeTP: Enabling Distributed Full-size Large Language Model Inference on Edge Devices with Tensor Parallelism.
Laizhong Cui, Yi Guo, Weixuan Peng, Yaodong Huang
Browse the full ICDCS paper archive.
Laizhong Cui, Yi Guo, Weixuan Peng, Yaodong Huang
Browse the full ICDCS paper archive.